microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224

zero-shot-image-classification
Maintenance lightby microsoft975.3K407updated 1 year ago

BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning.

README

language: en tags: clip biology medical license: mit libraryname: openclip widget: src: https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT256-vitbasepatch16224/resolve/main/exampledata/biomedimageclassificationexampledata/squamouscellcarcinomahistopathology.jpeg candidatelabels: adenocarcinoma histopathology, squamous cell carcinoma histopathology exampletitle: squamous cell carcinoma histopathology src: >-…

Source attribution

  • HuggingFacemicrosoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224

Related resources

Abstract:

8752 years ago
Python

darkknight25/deepseek-16b-medical-GPT is a fine-tuned version of deepseek-ai/deepseek-l6b-moe-chat, optimized for medical question answering, reasoning, and clinical summarization using QLoRA and open-access healthcare datasets.

010 months ago
Python

PPTStab: Prediction and Designing of thermostable proteins with a desired melting temperature

01 year ago
Python
6.2K3 weeks ago

> A CMR-report contrastive model combining Vision Transformers and pretrained text encoders.

1410 months ago

HuatuoGPT-o1-7B

5031 year ago